Intelligent presentation method

Abstract

Disclosed is an intelligent presentation method. The intelligent presentation method of the present disclosure may support a presentation to be smoothly performed by learning content of the presentation while a presenter is presenting and performing a function required for the presentation in response to a command voice. The intelligent presentation-assisting device of the present disclosure may be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.

What is claimed is: 
     
       1. An intelligent presentation method for controlling an intelligent presentation-assisting device, the method comprising:
 learning presentation content presented by a presenter; 
 recognizing a command voice uttered by the presenter during presentation of the presentation content; 
 analyzing, by an artificial intelligence (AI) processor, an intent of the presenter based on the presentation content and the command voice; 
 executing an operation corresponding to the command voice of the presenter based on the intent; 
 applying the command voice of the presenter to a pre-trained command voice recognition, determination and classification model to generate an application result; 
 determining whether a situation in which the command voice of the presenter is recognized correctly based on the application result to generate a determination result; 
 analyzing the intent of the presenter based on the determination result; and 
 receiving, via the 5G network, downlink control information (DCI) used to schedule transmission of information related to the situation in which the command voice of the presenter is recognized, 
 wherein the learning the presentation content includes learning the presentation content by acquiring first voice data uttered by the presenter and extracting first feature values of a first voice from the first voice data, 
 wherein the command voice recognition, determination and classification model is stored in a 5G network, 
 wherein the command voice recognition, determination and classification model is configured to receive, via the 5G network, the information related to the situation in which the command voice of the presenter is recognized and transmit, via the 5G network, a result of applying the command voice of the presenter to the command voice recognition, determination and classification model, and 
 wherein the information related to the situation in which the command voice of the presenter is recognized is transmitted via the 5G network based on the DCI. 
 
     
     
       2. The intelligent presentation method of  claim 1 , wherein the operation includes executing a function or responding with audio output or visual output. 
     
     
       3. The intelligent presentation method of  claim 1 , further comprising:
 recognizing text displayed on a screen as the presentation content; and 
 executing the operation corresponding to the command voice of the presenter based on the text and the intent. 
 
     
     
       4. The intelligent presentation method of  claim 1 , further comprising:
 converting the presentation content uttered by the presenter into text; and 
 executing the operation corresponding to the command voice based on the text and the intent. 
 
     
     
       5. The intelligent presentation method of  claim 1 , wherein the recognizing the command voice uttered by the presenter includes:
 comparing the first feature values of the first voice with the command voice of the presenter to generate a first comparison result; and 
 when the first comparison result is included in a set voice range, recognizing the command voice uttered by the presenter. 
 
     
     
       6. The intelligent presentation method of  claim 1 , wherein the recognizing the command voice uttered by the presenter includes:
 comparing the first feature values of the first voice with the command voice uttered by the presenter to generate a first comparison result; and 
 when the first comparison result is not included in a set voice range, not recognizing the command voice uttered by the presenter. 
 
     
     
       7. The intelligent presentation method of  claim 6 , further comprising:
 determining the presenter as a speaker and learning utterance content uttered from the speaker when the command voice of the presenter is not recognized, 
 wherein the learning the utterance content uttered by the speaker includes learning the utterance content by acquiring second voice data uttered by the speaker and extracting second feature values of a second voice from the second voice data. 
 
     
     
       8. The intelligent presentation method of  claim 7 , further comprising:
 recognizing a second command voice of the speaker in the utterance content; 
 analyzing a second intent of the speaker corresponding to the second command voice; and 
 executing a second operation corresponding to the second command voice of the speaker. 
 
     
     
       9. The intelligent presentation method of  claim 8 , wherein the recognizing the second command voice of the speaker includes:
 comparing the second feature values of the second voice with the second command voice of the speaker to generate a second comparison result; and 
 when the second comparison result is included in a set voice range, recognizing the second voice command of the speaker. 
 
     
     
       10. The intelligent presentation method of  claim 1 , wherein the command voice recognition, determination and classification model is stored in an external artificial intelligence (AI) device, and
 wherein the command voice recognition, determination and classification model is configured to: 
 receive, from the intelligent presentation-assisting device, feature values related to information related to a situation in which the command voice of the presenter is recognized; and 
 transmit, from the external AI device, a result of applying the command voice of the presenter to the command voice recognition, determination and classification model, to the intelligent presentation-assisting device. 
 
     
     
       11. The intelligent presentation method of  claim 1 , further comprising:
 controlling a communication unit to transmit the information related to the situation in which the command voice of the presenter is recognized to an AI processor included in the 5G network; and 
 controlling the communication unit to receive AI processed information from the AI processor, 
 wherein the AI processed information is information indicating whether the command voice of the presenter is recognized. 
 
     
     
       12. The intelligent presentation method of  claim 1 , further comprising:
 changing a page currently being presented to a next presentation page based on the command voice and the presentation content presented by the presenter. 
 
     
     
       13. The intelligent presentation method of  claim 1 , further comprising:
 identifying a plurality of presentation page candidates based on the command voice and the presentation content presented by the presenter; and 
 providing information about the plurality of presentation page candidates to the presenter. 
 
     
     
       14. An intelligent presentation-assisting device comprising:
 at least one microphone configured to receive voice input; and 
 a controller configured to:
 learn presentation content of a presentation presented by a presenter, 
 recognize a command voice uttered by the presenter during presentation of the presentation content, 
 analyze an intent of the presenter based on the presentation content and the command voice, 
 execute an operation corresponding to the command voice of the presenter based on the intent, 
 apply the command voice of the presenter to a pre-trained command voice recognition, determine and classification model to generate an application result, 
 determine whether a situation in which the command voice of the presenter is recognized correctly based on the application result to generate a determination result, 
 analyze the intent of the presenter based on the determination result, and 
 receive, via the 5G network, downlink control information (DC) used to schedule transmission of information related to the situation in which the command voice of the presenter is recognized, 
 
 wherein the learning the presentation content includes learning the presentation content by acquiring first voice data uttered by the presenter and extracting first feature values of a first voice from the first voice data, 
 wherein the command voice recognition, determination and classification model is stored in a 5G network, 
 wherein the command voice recognition, determination and classification model is configured to receive, via the 5G network, the information related to the situation in which the command voice of the presenter is recognized and transmit, via the 5G network, a result of applying the command voice of the presenter to the command voice recognition, determination and classification model, and 
 wherein the information related to the situation in which the command voice of the presenter is recognized is transmitted via the 5G network based on the DCI.